No, it has not. In the 1980s, 1990s, and early 00s, when clock speeds were doubling every 18-24 months Intel and the PC industry used Moore's Law as synonymous with doubling of performance in general and doubling of the clock speed specifically. Here is an example of this usage from the first paragraph of the National Academies of Sciences (NAS) 2010 report Sustaining Growth in Computing Performance authored by dozens of top figures in the chip industry and academic research.

http://sites.nationalacademies...

Fast, inexpensive computers are now essential for nearly all human endeavors and have been a critical factor in increasing economic productivity, enabling new defense systems, and advancing the frontiers of science. But less well understood is the need for ever-faster computers at ever-lower costs. For the last half-century, computers have been doubling in performance and capacity every couple of years. This remarkable, continuous, exponential growth in computing performance has resulted in an increase by a factor of over 100 per decade and more than a million in the last 40 years. For example, the raw performance of a 1970s supercomputer is now available in a typical modern cell phone. That uninterrupted exponential growth in computing throughout the lifetimes of most people has resulted in the expectation that such phenomenal progress, often called Moore's law, will continue well into the future.

Note that they are defining and using Moore's Law in this general way. The exponential improvement in performance of CPUs between the 1970s and 2003 was due almost entirely to the remarkable increase in the clock speed of the CPUs, not the number or density of transistors.

Since 2003 when clock speeds largely topped out, Intel and other chip companies have labored to distract attention from the clock speed. Why buy a new chip that is no faster than a chip from 14 years ago? Clock speeds have disappeared from the prominently displayed technical specifications displayed with PCs at stores and other venues. "Experts" are suddenly adamant that Moore's Law has nothing to do with clock speed: wherever did you get such as silly idea?

The reality is that the semiconductor technology has hit fundamental limits as frequently happens in the technology S curve seen in many historical technologies. Most probably a fundamentally new technology is needed -- much as jet engines are fundamentally different from propeller engines driven by internal combustion engines.

This reply to my comment is remarkably nasty and personal. This is after all Moore's Law and CPU speeds that is being discussed. "Liar" is used three times. "Dishonesty" one time. "Veracity" on time implying lying and dishonesty. The accusatory "you" is used at least twelve times. Moore's Law is a moving target. In the 1980s and 1990s, when CPU clock speeds were doubling every about 18-24 months the Intel marketing machine and much of the PC industry used Moore's Law as synonymous with the doubling clock speed. When the CPU speeds topped out in about 2003, they shifted to talking about increasing numbers of transistors and densities, multi-core chips etc. The clock speed numbers quickly disappeared from the technical specifications posted prominently in front of PCs in the stores. Moore's Law is a marketing gimmick and it changes. Whatever parameter is increasing dramatically becomes Moore's Law.

Moore's law is a moving target. The Intel marketing machine presented it as a doubling of clock speed every 18-24 months in the 1980s and 1990s when this was largely true. They shifted to emphasizing number of transistors/density of transistors when the clock speed largely topped out in about 2003 at around 2.3 GHz. Increases were doubling of clock speed in 18-24 months in much of 1980s and 1990s. Clock speed of Intel 8086 was 4.77 MHz in 1978. Intel heavily emphasized the clock speed improvements during this period. It is a marketing strategy. Whatever parameter is increasing rapidly is emphasized and becomes Moore's law.

CPU's and other chips used to double in speed about every 18-24 months, all the way from the early 1980s to about 2003. This is what used to be known as Moore's Law. It was long predicted that the standard semiconductor chips (CMOS etc.) would hit fundamental physics limitations when they reached very small feature sizes and very high clock rates, e.g. billions of cycles per second, some time in the early 2000s which is what appears to have happened. This is more generally known as the technology S curve where many technologies go through a period of very rapid, sometimes exponential improvement and then top out. This happened with propeller airplane engines from 1903 up to 1940s and then again with jet engines in the 1950's and 1960s. Once the top out is reached, usually a fundamental new technology such as jet engines in place of propeller engines, is needed to make a further leap: a 2X or better improvement. Probably a fundamentally new CPU technology, not current silicon chip technology, is needed to get to even higher clock speeds if it is even possible.

This is an audio announcement (0 Hours, 06 Minutes, 07 Seconds long) in MP3 audio format. Click on the link below to hear the audio message. If you need a MP3 player, you can use the free open-source Audacity program (http://audacity.sourceforge.net) available for Windows, Mac OS X, and Unix.

Listen Now

http://www.gftgroup.com/Guest/Petrana_Audio_Announ cement_75.mp3

  This audio mail was created using the Petrana Audio Mailer, a helper program for Microsoft Outlook and Outlook Express. The Petrana Audio Mailer enables recording and sending an audio mail message with three spoken commands, keystrokes, or button clicks with the mouse.

Available now at http://www.petrana.net/